Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to information and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to information and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parables
    -0.83
    aughs
    -0.75
    atos
    -0.74
    rine
    -0.71
    awar
    -0.70
    gg
    -0.70
    alone
    -0.69
    neys
    -0.67
    interstitial
    -0.66
    eled
    -0.66
    POSITIVE LOGITS
     overload
    1.06
     theoret
    1.00
     retrieval
    0.99
     glean
    0.95
    frame
    0.92
     dissemination
    0.85
     gathering
    0.83
     conveyed
    0.83
     gathered
    0.83
     literacy
    0.81
    Act Density 0.041%

    No Known Activations